CN102542799A - Line acquisition video vehicle detector based on pavement marker and detecting method thereof - Google Patents
Line acquisition video vehicle detector based on pavement marker and detecting method thereof Download PDFInfo
- Publication number
- CN102542799A CN102542799A CN2011104278489A CN201110427848A CN102542799A CN 102542799 A CN102542799 A CN 102542799A CN 2011104278489 A CN2011104278489 A CN 2011104278489A CN 201110427848 A CN201110427848 A CN 201110427848A CN 102542799 A CN102542799 A CN 102542799A
- Authority
- CN
- China
- Prior art keywords
- vehicle
- row
- pavement
- detecting device
- processor
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 238000000034 method Methods 0.000 title claims abstract description 19
- 239000003550 marker Substances 0.000 title abstract 3
- 238000001514 detection method Methods 0.000 claims abstract description 30
- 238000004891 communication Methods 0.000 claims abstract description 18
- 238000012545 processing Methods 0.000 claims abstract description 11
- 238000009434 installation Methods 0.000 claims description 8
- 239000000284 extract Substances 0.000 claims description 6
- 238000006243 chemical reaction Methods 0.000 claims description 4
- 238000004458 analytical method Methods 0.000 claims description 3
- 238000012544 monitoring process Methods 0.000 abstract description 3
- 238000013461 design Methods 0.000 description 8
- 230000006378 damage Effects 0.000 description 6
- 238000012360 testing method Methods 0.000 description 6
- 238000012423 maintenance Methods 0.000 description 4
- 230000000694 effects Effects 0.000 description 3
- 238000005516 engineering process Methods 0.000 description 3
- 238000002474 experimental method Methods 0.000 description 3
- 230000000630 rising effect Effects 0.000 description 3
- 238000005286 illumination Methods 0.000 description 2
- 230000011218 segmentation Effects 0.000 description 2
- 210000001367 artery Anatomy 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000000903 blocking effect Effects 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 238000009826 distribution Methods 0.000 description 1
- 238000003708 edge detection Methods 0.000 description 1
- 238000001914 filtration Methods 0.000 description 1
- 238000013507 mapping Methods 0.000 description 1
- 230000035800 maturation Effects 0.000 description 1
- 238000011160 research Methods 0.000 description 1
- 238000000638 solvent extraction Methods 0.000 description 1
- 238000012546 transfer Methods 0.000 description 1
Images
Landscapes
- Image Processing (AREA)
- Traffic Control Systems (AREA)
Abstract
The invention provides a line acquisition video vehicle detector based on a pavement marker, which comprises the following units: a camera, a processor, a storage and a GPRS (general packet radio service) communication module. The camera is used for acquiring pavement video information; the processor is used for extracting a pixel value of a line where a mark line is located and processing according to a set program; the storage is used for storing and reading data for the processor; and the GPRS communication module is used for feeding back the processing result to a server of a traffic monitoring centre. Meanwhile, the invention also discloses a detecting method of the detector, which is used for detecting the pavement traffic flow information in real time and detecting whether vehicles pass or not and counting the information such as the traffic volume, calculation of time occupation ratio of vehicles, vehicle speed, vehicle type and the like. The line acquisition video vehicle detector based on the pavement marker and the detecting method have the characteristics of high detection accuracy, small calculation redundancy and convenience in settings.
Description
Technical field
The present invention relates to the traffic monitoring field, particularly relate to a kind of video frequency vehicle detecting device.
Background technology
The classification of wagon detector has a variety of, and at present representative is is divided three classes it by the principle of work of detecting device: magnetic is wagon detector, ripple wagon detector and video frequency vehicle detecting device frequently frequently.
Magnetic is wagon detector frequently, mainly is the toroidal inductor wagon detector, and its detection method is accurate, and equipment is stable, technology maturation, and under severe weather conditions, still possess outstanding performance.But its installation and maintenance cost is high, need cut the road surface during installation so that have a strong impact on pavement life, and coil is buried underground on the way and damaged by pressure by vehicle (especially heavy goods vehicles) easily, needs road closure during maintenance, influences traffic flow.
Ripple detects frequently uses maximum have radar detector and laser detectors.Radar detector has and not traffic flow is not influenced by weather effect, installation and maintenance, the advantage that also need not to excavate original road surface, can detect many lane flow information simultaneously.Its major defect is to block up and large car is more, vehicle is announced uneven highway section in wagon flow, and because of blocking, its measuring accuracy can receive bigger influence, and is more high to the accuracy requirement of installing simultaneously.Laser vehicle checker and radar vehicle checker are similar, and cost an arm and a leg, so practical application is few.
The video frequency vehicle detecting device is to utilize video sensor, obtains the information of traffic scene in real time, utilizes mode identification technology, image processing techniques to wait to realize a kind of wagon detector of vehicle detection.The Video Detection advantage is to detect bigger traffic scene area, gathers more transport information; Small investment, expense are low; Equipment such as video sensor, camera for example is easy to install and debugging, and its software can be upgraded, and extensibility is good, long service life, and installation and maintenance can not broken and changed the road surface.
Video frequency vehicle mainly contains gray scale relative method, background subtraction point-score, frame difference method and edge detection method etc. in detecting.Yet still there are many problems in these detection methods in practical application.At first, road out of doors, remarkable change takes place in illumination condition in time, detection algorithm also will be got rid of the vehicle false retrieval that causes because of shade except adapting to the different illumination condition changes.Secondly, different vehicles differs greatly on size, color, and the vehicle identification difficulty is bigger, is prone to flase drop and omission situation.Once more, the quantity of information that video image comprises is bigger, and data redundancy is big, and the arithmetic capability of computing machine is limited at present, although many methods are feasible in theory, can not in practical application, satisfy real-time treatment requirement.
Summary of the invention
To the subject matter that exists in the present video vehicle checker testing process; The present invention provides a kind of base
to gather video frequency vehicle detecting device and detection method thereof in the row of pavement markers; Be used for detecting the road traffic stream information in real time, have the accuracy of detection height, calculate the characteristics of the little and convenient installation of redundance.
Technical scheme of the present invention is: provide a kind of row based on pavement markers to gather the video frequency vehicle detecting device, comprise following component units: camera is used to gather the road surface video information; Processor, extract the graticule place row pixel value and handle by setting detection algorithm; Storer is used for processor storage and reading of data; The GPRS communication module feeds back to result the server of traffic surveillance and control center.
Further, through integrated design, described camera, processor, storer and GPRS communication module integrate.
Further, said server like this, is realized exchanges data through GPRS communication module server and wagon detector through the algorithm parameter and the mode of operation of GPRS communication module setting wagon detector.
Further, said wagon detector has two kinds of mode of operations, when Installation and Debugging, adopts the pattern of output intact video images, makes camera aim detecting zone; When detecting, the pattern that adopts certain the row pixel value in the analysis video image to calculate, output telecommunication flow information.
As one of improving, said GPRS communication module inserts the internet, can share telecommunication flow information on the net.
Simultaneously, the invention also discloses the detection method of gathering the video frequency vehicle detecting device based on the row of pavement markers, may further comprise the steps: pavement strip is set; Processor extracts the pixel value of the row at graticule place from the video information of camera collection; Processor judges whether through detection algorithm that vehicle passes through and the time occupancy of statistical vehicle flowrate, calculating vehicle; The GPRS communication module sends to the time occupancy of vehicle flowrate, vehicle the server of traffic surveillance and control center through the GPRS module.
Further, said detection algorithm comprises following flow process: obtain the pavement strip data; Data are carried out DC processing; Data are carried out monolateral intermediate value binary conversion treatment; Destroyed area is detected; Vehicle count.
As one of improving, said pavement strip have 2 or more than, through the mistiming of comparison vehicle through the front and back graticule, the travel speed of measuring vehicle.
As one of improving, said detection method through comparison vehicle characteristics, is judged the vehicle of detected vehicle.
The invention has the beneficial effects as follows:
1, because when vehicle is detected; The present invention only gathers the pixel of certain delegation in the video, compares the common vehicle detecting device of gathering the complete video pixel, and its data volume reduces greatly; Realize the video acquisition of high frame per second easily, thereby improved the time precision of vehicle detection.The data volume of required processing is little, can use the single-chip microcomputer deal with data, has reduced the cost of wagon detector greatly.
2, the conventional video vehicle detection is that video is sent back supervisory control comuter, and by the supervisory control comuter deal with data, this method is higher to the configuration requirement of supervisory control comuter, and the road limited amount of monitoring.And the present invention just sends traffic flow data to supervisory control comuter fully by the microprocessor processes algorithm of wagon detector.In theory, use a supervisory control comuter just can accomplish the traffic flow collection of all roads.
3, the present invention is integrated into a portable wagon detector through integrated design with cam device, processor and GPRS communication module, and a plurality of track of road only need a vehicle checker, conveniently sets up, and reduces cost.
4, realize two kinds of mode of operations, both exportable complete video image, also exportable telecommunication flow information.When Installation and Debugging, can adopt the pattern of output intact video images, make camera aim detecting zone; When vehicle is detected, the pattern that adopts certain the row pixel in the analysis video image to calculate, output telecommunication flow information.
5, wagon detector can all weather operations under the situation that floor lights such as street lamp are arranged.Than traditional wagon detector, it is intensive that the present invention can solve wagon flow preferably, the vehicle detection problem when many cars are parallel, and average recognition rate reaches more than 95%, has higher using value.
Description of drawings
Fig. 1 is a structural representation of the present invention;
Fig. 2 is no car through state graticule gray-scale value curve at out-of-date night;
Fig. 3 has car through state graticule gray-scale value curve at out-of-date night;
Fig. 4 is that window size is 12 mean filter curve;
Fig. 5 is that window size is 36 mean filter curve;
Fig. 6 is the curve after the DC processing;
Fig. 7 is monolateral intermediate value split plot design threshold value synoptic diagram;
Fig. 8 is that no car is through out-of-date monolateral median method segmentation result;
Fig. 9 has car through out-of-date destroyed area testing result;
Figure 10 is single vehicle destroys number through out-of-date subregion a bar chart.
Embodiment
Fig. 1 is the capable structural representation of gathering the video frequency vehicle detecting device based on pavement markers provided by the invention, and comprise following component units: cam device is used to gather the road surface video information; Processor unit, extract the graticule place row pixel value and handle by setting program; Storage unit is used for processor storage and reading of data; The GPRS communication module feeds back to result the server of traffic surveillance and control center.Wherein processor is microprocessor MC9S12XS128, and the camera model is OV7620, and the GPRS communication module is EM310, integrates.Server is set the algorithm parameter and the mode of operation of wagon detector through the GPRS communication module.
Its concrete detection method is divided into following steps:
1, pavement strip is set, can utilizes existing walkway, also can draw voluntarily.
2, processor extracts the pixel value of the row at graticule place from the video information of camera collection.A scene instance with night is explained.Do not having car through out-of-date, the graticule data gray-scale value curve that collects is as shown in Figure 2, can find out that the rule of curvilinear motion meets the graticule characteristic distributions.Through out-of-date, the graticule data gray-scale value curve that collects is as shown in Figure 3 as car, and the local Changing Pattern of curve is destroyed.We have judged whether the car process through detecting this destruction.
Whether 3, processor is judged through detection algorithm has vehicle to pass through and the time occupancy of statistical vehicle flowrate, calculating vehicle.Its check algorithm specifically comprises following flow process:
3.1 mean filter
For filtering image noise, for the pavement strip data that collect, be window width with half of pavement strip block size, carry out mean filter.The filter effect of Fig. 3 is as shown in Figure 4.
3.2 DC processing
In order better to remove interference such as local light, shade, this patent has used the disposal route of removing direct current.DC processing is exactly that the data behind the wicket mean filter are deducted the data behind the big window mean filter, and the width of big window is decided to be three times of wicket width, for Fig. 4, and effect such as Fig. 5 behind the big window mean filter.The data that the data of Fig. 4 are deducted Fig. 5 just obtain the data behind the direct current, and are as shown in Figure 6.
3.3 monolateral intermediate value binary conversion treatment
For the local threshold split plot design, how to confirm that regional area is one of them important key.Traditional local threshold split plot design has just been considered some parameters such as variance, the average etc. in zone, and has lacked the consideration to provincial characteristics.The problem that in graticule is cut apart, exists to traditional local threshold; The present invention has used monolateral median method to confirm threshold value and split image; Though on applicability, be not so good as traditional local threshold split plot design; But cut apart in this certain applications at graticule, the performance of monolateral median method is much better than traditional local threshold split plot design.
Monolateral intermediate value partitioning algorithm principle: the supposition graticule is to be combined by some limits, as a spike occurs, can think that it is to be combined by two limits, so cutting apart of graticule just transfers cutting apart of limit to, is about to the limit and is decided to be a part and cuts apart.What used on every limit is that the maximal value on limit and the mean value of minimum value are cut apart as threshold value.
Analyze no car through the gray-scale value curve of out-of-date pavement strip through DC processing.As shown in Figure 7, the stain on every limit is represented the threshold value on this limit, and the threshold value on every limit equals the maximal value on this limit and the average of minimum value.Cutting apart of every limit is independently, and promptly the threshold value on a limit is only cut apart oneself, and can not influence other limits.
Segmentation result to Fig. 7 is as shown in Figure 8, and visible monolateral intermediate value split plot design can be good at cutting apart the uneven graticule data of gray scale, has very strong adaptability and practical value.
To there being car to carry out monolateral intermediate value binary conversion treatment through the gray-scale value curve of DC processing, can obtain curve map shown in Figure 9 through out-of-date pavement strip.
3.4 destroyed area detects
The basic thought of destroyed area detection algorithm is whether the distance between the graticule neighboring edge of judging after the monolateral intermediate value binaryzation meets the demands.Algorithm mainly was divided into for three steps:
1) for the graticule data after the monolateral intermediate value binaryzation
, the size through its first order derivative of computes
and positive and negative is judged saltus step and saltus step direction.
if
, expression detects the edge; if
, then the edge is a rising edge; if
, then the edge is a negative edge.
2) detect on the basis at edge in the first step, the intermarginal distance of opposite side is judged.Left side rising edge and the right negative edge are formed paddy, and left side negative edge and the right rising edge are formed the peak.Because the width of Gu Hefeng is not necessarily identical, we have defined, and whether paddy is wide indicates the graticule piece with peak width and is destroyed, and does not use absolute width, but provides a width range, and the edge outside width range is ruined edge.Destroy the edge and form destroyed area.
3) for detected destroyed area, regional width is judged in the zone that first combined distance is close again.If the width range in zone is ignored this destroyed area less than a threshold value (we are made as a width range that car is shared with it).For the zone of those width greater than threshold value, we just are decided to be final destroyed area with it.The part of looping among Fig. 9 is the last destroyed area of confirming.
3.5 vehicle count
For the convenience of vehicle count, graticule is divided into 25 wide sub regions.The destroyed area that obtains for the front; Through following method it is mapped in the subregion, establishes the subregion width for
:
1) marginal point on the graticule
is mapped to subregion, as shown in the formula:
Wherein
expression subarea number,
expression
divides exactly
.
2) establish the destroyed area left hand edge for
; Right hand edge is
; The subregion that then destroyed area is corresponding is to gather from the subregion that is numbered
to
, as shown in the formula.
Wherein
,
.
For the subregion of destroyed area mapping, can think that this sub regions is destroyed.Through an one-dimension array variable
is set;
is subarea number, adds up the ruined number of times of subregion.
The vehicle number increase need be satisfied following three conditions:
1) exist the destruction number of times to surpass the continuous subregion of threshold value A.Threshold value A is represented to detect several frames and is destroyed and thinks that just destroying is to produce through vehicle.According to the experiment situation, threshold value A is decided to be 5.
2) continuous subregion quantity is greater than threshold value B.On behalf of vehicle, the threshold value B here can destroy the Minimum Area number of subregion.According to the experiment situation, threshold value B is decided to be 4.
3) continuously subregion in continuous 2 frames of destruction number of each subregion do not change.
The destruction number of subregion needs zero clearing, under the condition that continuous 2 frames of the destruction number of subregion do not change, and does not satisfy three conditions that vehicle number increases, and the destruction number of subregion can automatic clear.In addition, continuous subregion zero clearing that also need it is corresponding when vehicle is successfully counted.Figure 10 is single vehicle destroys number through out-of-date subregion a bar chart.
Vehicle detecting algorithm in the processor to collect certain fixedly the pixel value of single file analyze and research, thereby judge whether vehicle passes through, calculate the vehicle time occupancy, judge traffic parameters such as vehicle, statistical vehicle flowrate.Further, two road signs are set,, can realize the function that tests the speed through the mistiming of comparison through the front and back road sign at certain distance.
4, system sends to server with each traffic flow parameter that processor calculates gained through the GPRS communication module.
Be the validity of checking detection method of the present invention for vehicle Flow Detection, test on several traffic main arteries in the Guangzhou, and test findings shows that average recognition rate is 97.45%.Actual detected result is as shown in table 1.
Table 1 wagon detector testing result table
| The experiment place | Time span/min | Mounting condition | Light condition | True quantity | Programmed counting | |
| Road | ||||||
| 1 | 10 | Just down | Daytime is bright | 448 | 449 | 99.78 |
| Road | ||||||
| 2 | 10 | Deflection | Daytime is bright | 690 | 657 | 95.22% |
| Road 3 | 10 | Just down | Daytime is bright | 680 | 658 | 96.76% |
| Road 3 | 10 | Just down | Daytime is bright | 625 | 594 | 95.04% |
| Road 3 | 10 | Just down | Daytime is bright | 590 | 573 | 97.12 |
| Road | ||||||
| 4 | 10 | Deflection | Daytime is bright | 640 | 600 | 93.75 |
| Road | ||||||
| 5 | 4 | Just down | Night is darker | 148 | 147 | 99.32 |
| Road | ||||||
| 6 | 10 | Just down | Daytime is bright | 443 | 444 | 99.77% |
| Road 7 | 10 | Just down | Daytime is bright | 385 | 384 | 99.74% |
| Road 7 | 10 | Just down | Daytime is bright | 386 | 389 | 99.22% |
| Road 7 | 10 | Just down | At dusk dark slightly | 406 | 407 | 99.75% |
Claims (9)
1. the row based on pavement markers is gathered the video frequency vehicle detecting device, it is characterized in that comprise following component units: camera is used to gather the road surface video information; Processor, extract the graticule place row pixel value and handle by setting detection algorithm; Storer is used for processor storage and reading of data; The GPRS communication module feeds back to result the server of traffic surveillance and control center.
2. the row based on pavement markers according to claim 1 is gathered the video frequency vehicle detecting device, it is characterized in that described camera, processor, storer and GPRS communication module integrate.
3. the row based on pavement markers according to claim 1 is gathered the video frequency vehicle detecting device, it is characterized in that, said server is set the algorithm parameter and the mode of operation of wagon detector through the GPRS communication module.
4. the row based on pavement markers according to claim 1 is gathered the video frequency vehicle detecting device; It is characterized in that said wagon detector has two kinds of mode of operations, when the Installation and Debugging car; Adopt the pattern of output intact video images, make camera aim detecting zone; When detecting, the pattern that adopts certain the row pixel value in the analysis video image to calculate, output telecommunication flow information.
5. the row based on pavement markers according to claim 1 is gathered the video frequency vehicle detecting device, it is characterized in that said GPRS communication module inserts the internet.
6. a detection method of gathering the video frequency vehicle detecting device based on the row of pavement markers is characterized in that, may further comprise the steps: pavement strip is set; Processor extracts the pixel value of the row at graticule place from the video information of camera collection; Processor judges whether through detection algorithm that vehicle passes through and the time occupancy of statistical vehicle flowrate, calculating vehicle; The GPRS communication module sends to the time occupancy information of vehicle flowrate, vehicle the server of traffic surveillance and control center through the GPRS module.
7. detection method of gathering the video frequency vehicle detecting device based on the row of pavement markers according to claim 2 is characterized in that said detection algorithm comprises following flow process: obtain the pavement strip data; Data are carried out DC processing; Data are carried out monolateral intermediate value binary conversion treatment; Destroyed area is detected; Vehicle count.
8. detection method of gathering the video frequency vehicle detecting device based on the row of pavement markers according to claim 2 is characterized in that, said pavement strip have 2 or more than, through the mistiming of comparison vehicle through the front and back graticule, the travel speed of measuring vehicle.
9. detection method of gathering the video frequency vehicle detecting device based on the row of pavement markers according to claim 2 is characterized in that, said detection method through comparison vehicle characteristics, is judged the vehicle of detected vehicle.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN2011104278489A CN102542799A (en) | 2011-12-19 | 2011-12-19 | Line acquisition video vehicle detector based on pavement marker and detecting method thereof |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN2011104278489A CN102542799A (en) | 2011-12-19 | 2011-12-19 | Line acquisition video vehicle detector based on pavement marker and detecting method thereof |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN102542799A true CN102542799A (en) | 2012-07-04 |
Family
ID=46349589
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN2011104278489A Pending CN102542799A (en) | 2011-12-19 | 2011-12-19 | Line acquisition video vehicle detector based on pavement marker and detecting method thereof |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN102542799A (en) |
Cited By (11)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103839415A (en) * | 2014-03-19 | 2014-06-04 | 重庆攸亮科技有限公司 | Traffic flow and occupation ratio information acquisition method based on road surface image feature identification |
| CN104064034A (en) * | 2013-03-24 | 2014-09-24 | 张生为 | Whole-process monitoring vehicle reminding system of highway |
| CN105869413A (en) * | 2016-06-23 | 2016-08-17 | 常州海蓝利科物联网技术有限公司 | Method for measuring traffic flow and speed based on camera video |
| CN106170072A (en) * | 2016-07-18 | 2016-11-30 | 中国科学院地理科学与资源研究所 | Video acquisition system and acquisition method thereof |
| CN107462741A (en) * | 2017-07-26 | 2017-12-12 | 武汉船用机械有限责任公司 | A kind of moving object speed and acceleration measurement device |
| CN107707587A (en) * | 2016-08-09 | 2018-02-16 | 南昌欧菲智慧信息产业有限公司 | Control method, server, wagon detector and vehicle detecting system |
| CN109073393A (en) * | 2016-04-08 | 2018-12-21 | 罗伯特·博世有限公司 | Method for determining the attitude of an at least partially autonomous vehicle by means of landmarks which are specially selected and transmitted by a back-end server |
| CN109285170A (en) * | 2017-07-22 | 2019-01-29 | 周尧 | A kind of Local threshold segmentation method |
| CN109285352A (en) * | 2017-07-22 | 2019-01-29 | 周尧 | A kind of vehicle checking method based on pavement markers |
| CN109285161A (en) * | 2017-07-22 | 2019-01-29 | 周尧 | A kind of unilateral intermediate value partitioning algorithm |
| CN112419748A (en) * | 2019-08-20 | 2021-02-26 | 广州中广国科测控技术有限公司 | Image speed measuring method using road marking |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN2442334Y (en) * | 2000-09-08 | 2001-08-08 | 叶玉飞 | Video car flow detector |
| CN2553460Y (en) * | 2002-07-04 | 2003-05-28 | 深圳市哈工大交通电子技术有限公司 | Video frequency traffic state information collecting device |
| CN101469985A (en) * | 2007-12-26 | 2009-07-01 | 河海大学常州校区 | Single-frame image detection apparatus for vehicle queue length at road junction and its working method |
| CN201429904Y (en) * | 2009-06-29 | 2010-03-24 | 长安大学 | Statistical system of traffic flow |
| CN101706998A (en) * | 2009-11-12 | 2010-05-12 | 宁波工程学院 | Intelligent traffic signal control terminal |
| CN102184635A (en) * | 2011-04-22 | 2011-09-14 | 北京文安科技发展有限公司 | Low-power-consumption high-definition-video illegality monitoring system |
-
2011
- 2011-12-19 CN CN2011104278489A patent/CN102542799A/en active Pending
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN2442334Y (en) * | 2000-09-08 | 2001-08-08 | 叶玉飞 | Video car flow detector |
| CN2553460Y (en) * | 2002-07-04 | 2003-05-28 | 深圳市哈工大交通电子技术有限公司 | Video frequency traffic state information collecting device |
| CN101469985A (en) * | 2007-12-26 | 2009-07-01 | 河海大学常州校区 | Single-frame image detection apparatus for vehicle queue length at road junction and its working method |
| CN201429904Y (en) * | 2009-06-29 | 2010-03-24 | 长安大学 | Statistical system of traffic flow |
| CN101706998A (en) * | 2009-11-12 | 2010-05-12 | 宁波工程学院 | Intelligent traffic signal control terminal |
| CN102184635A (en) * | 2011-04-22 | 2011-09-14 | 北京文安科技发展有限公司 | Low-power-consumption high-definition-video illegality monitoring system |
Cited By (15)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104064034A (en) * | 2013-03-24 | 2014-09-24 | 张生为 | Whole-process monitoring vehicle reminding system of highway |
| CN103839415B (en) * | 2014-03-19 | 2016-08-24 | 重庆攸亮科技股份有限公司 | Traffic flow based on pavement image feature identification and occupation rate information getting method |
| CN103839415A (en) * | 2014-03-19 | 2014-06-04 | 重庆攸亮科技有限公司 | Traffic flow and occupation ratio information acquisition method based on road surface image feature identification |
| CN109073393A (en) * | 2016-04-08 | 2018-12-21 | 罗伯特·博世有限公司 | Method for determining the attitude of an at least partially autonomous vehicle by means of landmarks which are specially selected and transmitted by a back-end server |
| CN105869413A (en) * | 2016-06-23 | 2016-08-17 | 常州海蓝利科物联网技术有限公司 | Method for measuring traffic flow and speed based on camera video |
| CN106170072A (en) * | 2016-07-18 | 2016-11-30 | 中国科学院地理科学与资源研究所 | Video acquisition system and acquisition method thereof |
| CN106170072B (en) * | 2016-07-18 | 2022-06-10 | 中国科学院地理科学与资源研究所 | Video acquisition system and acquisition method thereof |
| CN107707587A (en) * | 2016-08-09 | 2018-02-16 | 南昌欧菲智慧信息产业有限公司 | Control method, server, wagon detector and vehicle detecting system |
| CN107707587B (en) * | 2016-08-09 | 2021-11-12 | 南昌欧菲智慧信息产业有限公司 | Control method, server, vehicle detector and vehicle detection system |
| CN109285170A (en) * | 2017-07-22 | 2019-01-29 | 周尧 | A kind of Local threshold segmentation method |
| CN109285352A (en) * | 2017-07-22 | 2019-01-29 | 周尧 | A kind of vehicle checking method based on pavement markers |
| CN109285161A (en) * | 2017-07-22 | 2019-01-29 | 周尧 | A kind of unilateral intermediate value partitioning algorithm |
| CN107462741B (en) * | 2017-07-26 | 2019-12-31 | 武汉船用机械有限责任公司 | Moving object speed and acceleration measuring device |
| CN107462741A (en) * | 2017-07-26 | 2017-12-12 | 武汉船用机械有限责任公司 | A kind of moving object speed and acceleration measurement device |
| CN112419748A (en) * | 2019-08-20 | 2021-02-26 | 广州中广国科测控技术有限公司 | Image speed measuring method using road marking |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN102542799A (en) | Line acquisition video vehicle detector based on pavement marker and detecting method thereof | |
| CN104751634B (en) | The integrated application method of freeway tunnel driving image acquisition information | |
| CN102385803B (en) | All-weather urban vehicle tracking and counting method based on video monitoring | |
| CN102289940B (en) | Hybrid differential-based traffic flow detection method | |
| CN100403332C (en) | Vehicle lane Robust identifying method for lane deviation warning | |
| KR100459476B1 (en) | Apparatus and method for queue length of vehicle to measure | |
| CN103714363B (en) | A kind of motor vehicle exhaust smoke video identification system | |
| CN110287905B (en) | Deep learning-based real-time traffic jam area detection method | |
| CN101339616B (en) | Roads recognition method and apparatus | |
| Pan et al. | Traffic surveillance system for vehicle flow detection | |
| CN107301776A (en) | Track road conditions processing and dissemination method based on video detection technology | |
| CN103366571A (en) | Intelligent method for detecting traffic accident at night | |
| CN106127113A (en) | A kind of road track line detecting method based on three-dimensional laser radar | |
| CN103077617A (en) | Pedestrian crosswalk intelligent traffic light monitoring system and method based on computer vision | |
| CN102005120A (en) | Traffic intersection monitoring technology and system based on video image analysis | |
| CN101470807A (en) | Accurate detection method for highroad lane marker line | |
| CN102819764A (en) | Method for counting pedestrian flow from multiple views under complex scene of traffic junction | |
| CN102110366B (en) | Block-based accumulated expressway vehicle parking event detecting method | |
| CN103295403A (en) | Traffic flow visual inspection method | |
| CN114329074B (en) | Traffic energy efficiency detection method and system for ramp road section | |
| CN110659552A (en) | Tramcar obstacle detection and alarm method | |
| CN108520528B (en) | Mobile vehicle tracking method based on improved difference threshold and displacement matching model | |
| Zhu et al. | A real-time vision system for automatic traffic monitoring based on 2D spatio-temporal images | |
| Iwasaki et al. | Real-time robust vehicle detection through the same algorithm both day and night | |
| CN109285352A (en) | A kind of vehicle checking method based on pavement markers |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| C10 | Entry into substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| C02 | Deemed withdrawal of patent application after publication (patent law 2001) | ||
| WD01 | Invention patent application deemed withdrawn after publication |
Application publication date: 20120704 |